blog-post-writer
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user data in the form of thoughts, articles, and links, which presents a surface for indirect prompt injection attacks.
- Ingestion points: User input is received in the first step of the workflow defined in SKILL.md.
- Boundary markers: No delimiters or instructions to ignore embedded commands are present in the prompt instructions.
- Capability inventory: The skill has the capability to perform external network requests (via the image generation script) and local file system write operations.
- Sanitization: No sanitization or validation of external content is performed before processing.
- [EXTERNAL_DOWNLOADS]: The script scripts/generate_image_seedream.py makes a network request to the external domain api.gptnb.ai to generate images based on prompts.
- [COMMAND_EXECUTION]: The skill is instructed to create new files on the local file system (e.g., 标题.md) to save the generated blog posts.
Audit Metadata